Semantic Matching by Non-Linear Word Transportation for Information Retrieval
By Jiafeng Guo, Yixing Fan, Qingyao Ai, W. Bruce Croft. 2016
77 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Systems, Information Retrieval & Search
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Jamie Callan
- Chenyan Xiong
- Zhuyun Dai
- Zhiyuan Liu
- Jimmy J. Lin
- Andrew Yates
- W. Bruce Croft
- Jiafeng Guo
In Computer Vision and Pattern Recognition
- Jamie Callan
- Chenyan Xiong
- Zhuyun Dai
- Zhiyuan Liu
- Yongfeng Zhang
- Qingyao Ai
- Yixing Fan
- W. Bruce Croft
In Information Systems
- Jamie Callan
- Zhuyun Dai
- Chenyan Xiong
- Zhiyuan Liu
- Yongfeng Zhang
- Jiafeng Guo
- Qingyao Ai
- Jimmy J. Lin
In Information Retrieval & Search
- Jamie Callan
- Chenyan Xiong
- Zhuyun Dai
- Zhiyuan Liu
- Andrew Yates
- Jimmy J. Lin
- Jiafeng Guo
- W. Bruce Croft
Citations in the corpus
- End-to-End Neural Ad-hoc Ranking with Kernel Pooling (2017, background): “Exact match of query words to document words is a strong signal of relevance [8], whereas so-match is a weaker signal that must be used carefully.”
- Modeling Diverse Relevance Patterns in Ad-hoc Retrieval (2018, unknown): “Following the idea in [11], term vectors are employed as basic representations so that rich semantic relations between query and document terms can be captured.”
- PROP: Pre-training with Representative Words Prediction for Ad-hoc Retrieval (2020, methodology): “Besides the above baselines, we also compare PROPwith existing state-of-the-art models (SOTA) on these five datasets, including CEDR-KNRM [21] on Robust04, BERT-maxP [10] on ClueWeb09-B, NWT [15] on Gov2, and HiNT [13] on MQ2007 and MQ2008.”
- Explainable Product Search with a Dynamic Relation Embedding Model (2019, background): “previous studies [18, 19], the main difference between unigram models and latent space models is their ability to conduct semantic matching.”
- Convolutional Neural Networks for Soft-Matching N-Grams in Ad-hoc Search (2018, unknown): “To overcome this problem, word embeddings [20] are introduced to calculate the translation scores [12].”
- Retrieving Textual Evidence for Knowledge Graph Facts (2019, background): “Recent results hint at these challenges [8, 11].”
- A Survey of Model Architectures in Information Retrieval (2025, unknown): “Word Embeddings In addition to advancements in network architecture, pre-trained textual representations have also contributed to neural ranking models’ performance (Guo et al., 2016b).”